xAI cuts grok-4.5 cached input to $0.30 per 1M tokens
xAI lowered cached input on its grok-4.5 flagship from $0.50 to $0.30 per 1M tokens, a 40% cut that widens the prompt-caching discount on the newest Grok model.
grok-4.5 cached input: $0.50 per 1M tokens, against a $2.00 cache-miss input rate.
grok-4.5 cached input: $0.30 per 1M tokens short context and $0.60 long context, against the same $2.00 cache-miss input rate.
Uncached grok-4.5 rates are unchanged at $2.00 input / $6.00 output per 1M tokens (500k context). Only the cached-input line moved, from $0.50 to $0.30, bringing grok-4.5’s cache discount ratio closer to the one grok-4.3 already offered at $0.20 against a $1.25 cache-miss rate.
The cut lands alongside xAI’s new long-context rate column, where grok-4.5 cached input is $0.60 per 1M tokens. Repeat-context agent workloads on the flagship — the ones that reuse a large system prompt or document across many calls — see the largest benefit.
xAI merges the separate Code API and Chat API rate tables into a single Text API table and adds a second rate column for long context, roughly 2x the short-context rate: grok-4.5 $4.00 in / $0.60 cached / $12.00 out, grok-4.3 and the grok-4.20 variants $2.50 / $0.40 / $5.00, grok-build-0.1 $2.00 / $0.40 / $4.00. Crossing a model's long-context threshold reprices every token in that request, not just the tokens past the line. In the same release grok-4.5 cached input drops from $0.50 to $0.30 per 1M tokens (-40%), while short-context headline rates, agentic tool rates, Batch (−20%), Priority (2x) and consumer plans are unchanged. (Source: docs.x.ai/docs/pricing, live capture 2026-07-21.)